deepseek/deepseek-v3.1

deepseek-ai/Deepseek-V3.1

Context

100K

Input

text

Output

text

Tool calling

Supported

About this model

DeepSeek-V3.1 is a 1.3T-parameter Mixture-of-Experts model with 236B active parameters per token. It features enhanced reasoning capabilities, extended 1M token context window, and improved multilingual support with advanced tool usage and code generation capabilities.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita

Available

Input tokens

$0.270 / 1M tokens

Output tokens

$1.000 / 1M tokens

Routing

OneInfer optimized

Thinking Machines

Available

Input tokens

$1.695 / 1M tokens

Output tokens

$4.215 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.270 / 1M tokens
Output tokens	$1.000 / 1M tokens

Performance

Published evaluation results associated with this model.

Reasoning

GSM8K95.8

ARC-Challenge93.4

BBH85.7

TheoremQA78.3

Coding

HumanEval84.6

MBPP87.2

MultiPL-E82.1

RepoBench79.8

Multilingual

XTREME87.3

Flores-20083.6

CMMLU90.2

JiaoZi88.7

Long-Context

NeedleInAHaystack99.1

LongBench89.5

Scrolls85.2

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/Deepseek-V3.1",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'